Parallel Programming in Fortran 95 using OpenMP - People

More documents

Recommendations

Info

$Intel(R) Math Kernel Library for Linux* OS User's Guide$

70 5. The environment variables 5.1 OMP NUM THREADS This environment variable specifies the number of threads to be used during execution of the parallel regions inside an OpenMP-parallel program. In principle, any integer number greater than 0 can be set as the number of threads to be used, although if this number is larger than the number of available physical processors, then the parallel running program will in general be very slow! When dynamic adjustment of the number of threads is enabled, the value given in OMP NUM THREADS represents the maximum number of threads allowed. Examples showing the syntaxis corresponding to Linux/Unix systems using the csh and bash shells are, respectively: > setenv OMP_NUM_THREADS 16 > OMP_NUM_THREADS=16 > export OMP_NUM_THREADS 5.2 OMP SCHEDULE This environment variable affects the way in which !$OMP DO and !$OMP PARALLEL DO directives work, if they have their scheduling set to RUNTIME: !$OMP DO SCHEDULE(RUNTIME) The schedule type and chunk size for all such loops can be specified at run time by setting this environment variable to any of the recognized schedule types and to an optional chunk size, using the same notation as inside the SCHEDULE clause. The possible schedule types are STATIC, DYNAMIC or GUIDED: descriptions of them can be found in the explanation of the !$OMP DO directive. The default value for the OMP SCHEDULE environment variable is OpenMP-implementation dependent, so it is necessary to look at its documentation in order to know that. If the optional chunk size is not set, a chunk size of 1 is assumed, except in the case of a STATIC schedule, where the default chunk size is set equal to the total number of do-loop iterations divided by the number of threads which act on the parallelized do-loop. Examples showing the syntaxis corresponding to Linux/Unix systems using the csh and bash shells are, respectively: > setenv OMP_SCHEDULE "GUIDED,4" > OMP_SCHEDULE=dynamic > export OMP_SCHEDULE
5.3. OMP DYNAMIC 71 5.3 OMP DYNAMIC In large SMP machines it is common that several different programs share the available resources of the machine. Under such conditions it can happen that fixing the number of threads to be used inside the parallel regions of a program may lead to unefficient use of the resources. Therefore, it is possible to enable the run-time environment of the SMP machine to adjust the number of threads dynamically, in order to maximize the use of the machine. This is done through the present environment variable which can be set equal to TRUE, if dynamic assignment is allowed, or equal to FALSE, if a fixed number of threads are to be used. The default value for the OMP DYNAMIC environment variable is OpenMP-implementation dependent, so it is necessary to look at its documentation in order to know that. Examples showing the syntaxis corresponding to Linux/Unix systems using the csh and bash shells are, respectively: > setenv OMP_DYNAMIC TRUE > OMP_DYNAMIC=FALSE > export OMP_DYNAMIC 5.4 OMP NESTED This environment variable specifies what the run-time environment has to do, when nested OpenMP directives are found. If its value is set equal to TRUE, nested parallelism is enabled and a new set of threads forming a new team is created to work on the nested directive. The result is a tree structure as shown in figure 1.2, for the case of using two threads at each level of nesting. If the environment variable OMP NESTED is set equal to FALSE, then the nested directives are serialized; that is, they are executed by a team with only one thread. Examples showing the syntaxis corresponding to Linux/Unix systems using the csh and bash shells are, respectively: > setenv OMP_NESTED TRUE > OMP_NESTED=FALSE > export OMP_NESTED
Page 1:
Parallel Programming in Fortran 95
Page 4 and 5:
ii CONTENTS 3.1.4 FIRSTPRIVATE(list
Page 6 and 7:
2 1. OpenMP Fortran Application Pro
Page 8 and 9:
Page 10 and 11:
Page 12 and 13:
Page 14 and 15:
10 2. OpenMP constructs • Work-sh
Page 16 and 17:
12 2. OpenMP constructs real(8) ::
Page 18 and 19:
14 2. OpenMP constructs do k = 1, 1
Page 20 and 21:
16 2. OpenMP constructs !$OMP SECTI
Page 22 and 23:
18 2. OpenMP constructs thread 0 th
Page 24 and 25: 20 2. OpenMP constructs • If the
Page 26 and 27: 22 2. OpenMP constructs 2.3 Synchro
Page 28 and 29: 24 2. OpenMP constructs thread 0 th
Page 30 and 31: 26 2. OpenMP constructs thread 0 th
Page 32 and 33: 28 2. OpenMP constructs !$OMP DO do
Page 34 and 35: 30 2. OpenMP constructs 2.3.6 !$OMP
Page 36 and 37: 32 2. OpenMP constructs !$OMP END D
Page 38 and 39: 34 2. OpenMP constructs Shared memo
Page 40 and 41: 36 2. OpenMP constructs
Page 42 and 43: 38 3. PRIVATE, SHARED & Co. Shared
Page 46 and 47: 42 3. PRIVATE, SHARED & Co. In this
Page 50 and 51: 46 3. PRIVATE, SHARED & Co. Operato
Page 52 and 53: 48 3. PRIVATE, SHARED & Co. it is n
Page 54 and 55: 50 3. PRIVATE, SHARED & Co. DYNAMIC
Page 56 and 57: 52 3. PRIVATE, SHARED & Co. Pieces
Page 58 and 59: 54 3. PRIVATE, SHARED & Co.
Page 60 and 61: 56 4. The OpenMP run-time library T
Page 62 and 63: 58 4. The OpenMP run-time library d
Page 64 and 65: 60 4. The OpenMP run-time library 4
Page 66 and 67: 62 4. The OpenMP run-time library T
Page 68 and 69: 64 4. The OpenMP run-time library I
Page 70 and 71: 66 4. The OpenMP run-time library 4
Page 72 and 73: 68 4. The OpenMP run-time library i
show all

Parallel Programming in Fortran 95 using OpenMP - People

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?